Voice interaction for Claude Code. Use when users mention voice mode, speak, talk, converse, voice status, or voice troubleshooting.
Installation
Details
Usage
After installing, this skill will be available to your AI coding assistant.
Verify installation:
skills listSkill Instructions
name: voicemode description: Voice interaction for Claude Code. Use when users mention voice mode, speak, talk, converse, voice status, or voice troubleshooting.
First-Time Setup
If VoiceMode isn't working or MCP fails to connect, run:
/voicemode:install
After install, reconnect MCP: /mcp → select voicemode → "Reconnect" (or restart Claude Code).
VoiceMode
Natural voice conversations with Claude Code using speech-to-text (STT) and text-to-speech (TTS).
Note: The Python package is voice-mode (hyphen), but the CLI command is voicemode (no hyphen).
When to Use MCP vs CLI
| Task | Use | Why |
|---|---|---|
| Voice conversations | MCP voicemode:converse | Faster - server already running |
| Service start/stop | MCP voicemode:service | Works within Claude Code |
| Installation | CLI voice-mode-install | One-time setup |
| Configuration | CLI voicemode config | Edit settings directly |
| Diagnostics | CLI voicemode diag | Administrative tasks |
Usage
Use the converse MCP tool to speak to users and hear their responses:
# Speak and listen for response (most common usage)
voicemode:converse("Hello! What would you like to work on?")
# Speak without waiting (for narration while working)
voicemode:converse("Searching the codebase now...", wait_for_response=False)
For most conversations, just pass your message - defaults handle everything else.
| Parameter | Default | Description |
|---|---|---|
message | required | Text to speak |
wait_for_response | true | Listen after speaking |
voice | auto | TTS voice |
For all parameters, see Converse Parameters.
Best Practices
- Narrate without waiting - Use
wait_for_response=Falsewhen announcing actions - One question at a time - Don't bundle multiple questions in voice mode
- Check status first - Verify services are running before starting conversations
- Let VoiceMode auto-select - Don't hardcode providers unless user has preference
- First run is slow - Model downloads happen on first start (2-5 min), then instant
Check Status
voicemode service status # All services
voicemode service status whisper # Specific service
Shows service status including running state, ports, and health.
Installation
# Install VoiceMode CLI and configure services
uvx voice-mode-install --yes
# Install local services (Apple Silicon recommended)
voicemode service install whisper
voicemode service install kokoro
See Getting Started for detailed steps.
Service Management
# Start/stop services
voicemode:service("whisper", "start")
voicemode:service("kokoro", "start")
# View logs for troubleshooting
voicemode:service("whisper", "logs", lines=50)
| Service | Port | Purpose |
|---|---|---|
| whisper | 2022 | Speech-to-text |
| kokoro | 8880 | Text-to-speech |
| livekit | 7880 | Real-time rooms |
Actions: status, start, stop, restart, logs, enable, disable
Configuration
voicemode config list # Show all settings
voicemode config set VOICEMODE_TTS_VOICE nova # Set default voice
voicemode config edit # Edit config file
Config file: ~/.voicemode/voicemode.env
See Configuration Guide for all options.
CLI Cheat Sheet
# Service management
voicemode service status # All services
voicemode service start whisper # Start a service
voicemode service logs kokoro # View logs
# Diagnostics
voicemode deps # Check dependencies
voicemode diag info # System info
voicemode diag devices # Audio devices
# History search
voicemode history search "keyword"
voicemode history play <exchange_id>
Documentation Index
| Topic | Link |
|---|---|
| Converse Parameters | All Parameters |
| Installation | Getting Started |
| Configuration | Configuration Guide |
| Claude Code Plugin | Plugin Guide |
| Whisper STT | Whisper Setup |
| Kokoro TTS | Kokoro Setup |
| Pronunciation | Pronunciation Guide |
| Troubleshooting | Troubleshooting |
| CLI Reference | CLI Docs |
